I wonder how far you can push RAG and it's comparison to methods like LoRA
https://github.com/microsoft/LoRA
It seems like you can only get so far with a sophisticated prompt engineering framework like RAG. but I dunno, I haven't tested them against each other.
I wonder how far you can push RAG and it's comparison to methods like LoRA
https://github.com/microsoft/LoRA
It seems like you can only get so far with a sophisticated prompt engineering framework like RAG. but I dunno, I haven't tested them against each other.